A Federated Cognitive Digital Twin (FCDT) architecture that combines federation and cognition within a unified approach improves scalability, responsiveness, and decision-making in complex distributed CPSs.
Abstract
Digital Twins (DTs) are increasingly adopted to monitor, analyze, and optimize Cyber-Physical Systems (CPSs) through continuous interaction between physical assets and their digital counterparts. However, current DT architectures often rely on centralized and monolithic designs, leading to scalability, latency, and resilience issues in distributed environment such as smart cities. Moreover, they provide limited support for semantic integration and high-level reasoning, reducing the effectiveness of DT-based decision-making. Recent studies on Federated Digital Twins (FDTs) have addressed scalability by decomposing complex systems into interacting twins, but they still largely centralize intelligence in cloud components. In parallel, Cognitive Digital Twins (CDTs) enhance DTs with semantic reasoning, explainability, and AI-driven decision support, yet they are typically difficult to integrate into distributed architectures. This paper proposes a Federated Cognitive Digital Twin (FCDT) architecture that combines federation and cognition within a unified approach. The architecture distributes intelligence across the edge-to-cloud continuum through local twins, which provide real-time monitoring and lightweight cognitive capabilities, and global twins, which perform system-level reasoning, simulation, and coordination. By integrating distributed autonomy with cognitive reasoning, the proposed approach improves scalability, responsiveness, and decision-making in complex distributed CPSs
Heterogeneous multi-UAV fleets act as highly dynamic mobile Internet of Things (IoT) nodes, but they often integrate platforms with incompatible telemetry and control semantics, hindering safe and scalable coordination. This paper presents an Asset Administration Shell (AAS)-driven digital twin architecture for the cloud continuum that decouples protocol translation from mission orchestration, pushing compute power closer to the edge. The first contribution of this work is a four-layer communication model mapped across the IoT and edge continuum, spanning physical-digital synchronization at the network edge, inter-digital-twin interaction, digitaltwin/GCS supervision in the fog/cloud layer, and a safety-critical physical/GCS bypass. The second contribution is a UAV AAS submodel that standardizes runtime state, energy, payload, and wireless QoS descriptors. The third contribution is an analytical validation framework based on bounded digital-twin staleness $\left(\Delta S_{\max }=30 ~\text{ms}\right)$ to evaluate semantic task reallocation and QoS-aware telemetry adaptation. At a representative cruise speed of 15 m/s, the worst-case position uncertainty induced by semantic latency is 0.45 m, which is acceptable for highlevel mission handoff. For degraded links, stability conditions are derived for queue-bounded latest-state forwarding and hysteresis-based telemetry control. The analysis indicates that AAS enables protocol-agnostic interoperability while preserving orchestration timeliness.
M. Bampi, P. H. M. Pereira, E. P. de Freitas· International Conference on...· 0 citations
Fusing digital twins (DTs) with world models (WMs) promises a leap from reactive monitoring to proactive control. However, deploying high-fidelity WMs faces a fundamental cognitive gap: the immense computational demand of foundation models conflicts with the resource constraints of 6G edge nodes, while privacy regulations hinder the centralization of raw sensory data required for training. To bridge this gap, this paper presents HongAvg, a hierarchical on-demand cognitive split federated learning framework designed as cognitive infrastructure for next-generation DTs. By establishing a national-basin-edge three-tier architecture, HongAvg introduces foundation models to resource-constrained edges via split computing, offloading heavy cognitive reasoning while preserving data privacy. We propose a dual-stream semantic consistency mechanism to align edge interactions with the foundation model's cognition, ensuring that distributed cognitive primitives serve as valid inputs for global state estimation. Validated on a heterogeneous benchmark, HongAvg serves as a prototype for industrial cognitive computing, improving accuracy in visual monitoring by up to 8.9% and reducing edge memory usage by approximately 75%. This work provides the scalable architectural prerequisite necessary for evolving static DTs into proactive WM-driven multi-agent orchestrated intelligent systems.
Yue Wang, Jixuan Xie, Yusheng Lin et al.· IEEE Transactions on Network...· 0 citations
The increasing deployment of Internet of Things (IoT) infrastructures in smart environments is enabling the continuous generation of heterogeneous data from devices, services and stakeholders, facilitating the interconnection between physical and digital entities. However, many current solutions still process such data in a fragmented manner, with limited support for cross-domain contextualization, real-time reasoning, and distributed intelligence. In parallel, Digital Twins (DTs) emerge as a promising paradigm for representing and managing complex smart systems, yet many existing approaches still lack a clear path from context-aware IoT data processing to operational, adaptive, and collaborative twins. This paper presents a research roadmap from Collaborative IoT and context awareness toward DTs and Systems of Systems (SoS) of DTs, grounded in our previous work on context-aware service architectures, homogeneous context representation, real-time event correlation, and distributed processing across the computing continuum. The roadmap is structured around three complementary directions: context-aware models for adaptive and intelligent DT behavior, composability, collaboration and hybrid intelligence in systems and SoS of DTs, and servitization and augmentation in DT ecosystems. The paper also identifies ongoing research efforts and the key challenges that must be addressed to enable the practical realization of this roadmap.
Guadalupe Ortiz, A. García-de-Prado, Andrés Muñoz et al.· International Symposium on S...· 0 citations
The 6G networks require autonomous and smart management of resources to support ultra-dense devices, dynamic traffic and low-latency services. The classic methods of Network Function Virtualization (NFV) orchestration utilize primarily the use of either a static or heuristics algorithm, which constrains their capacity to adjust to the dynamically evolving network conditions. Additionally, the current digital twin and distributed learning systems are characterized by a high level of synchronization overhead and poor automation abilities. To cope with these issues, this paper suggests a Federated Intelligence-based Digital Twin-Assisted Intent-Directed Autonomous Virtual Network Function (VNF) Orchestration. The proposed methodology combines the idea of digital twins to represent a real-time network with the idea of federated learning so that one can train models using a set of distributed edge nodes and maintain data privacy. In Python, the machine learning model is applied to interpret the network traffic data and forecast the demands of resources to be efficient in the orchestration of VNF. The experimental findings indicate that the suggested framework with such a high prediction precision of about 98, a higher usage of resources and a lower latency rate. The paper concluded that incorporating digital twins and federated intelligence could be useful in future 6G networks management to achieve high degrees of automation, scalability, and resilience.
Kishore Golla, M. Ramkumar· 2026 4th International Confe...· 0 citations
Managing resources across IoT, edge, and cloud layers calls for continuous, context-aware decisions under constraints that rarely stay fixed. Deep reinforcement learning (DRL) handles this class of problems well, and large language models (LLMs) are increasingly used to augment DRL pipelines, yet the architectural relationship between the two is seldom made explicit. We build on Wang et al.'s taxonomy of Continuum Orchestration Systems employing DRL techniques and extend it with two further dimensions. The AI Augmentation Paradigm measures how LLMs are exploited, while the Feedback channel captures whether and through which system path the execution feedback returns to the LLM in order to close the MAPE control loop at the LLM Orchestration layer. We apply this taxonomy to six recent system architectures and find a common gap, as none combines full LLM orchestration with full agent-layer feedback in a Cloud Continuum setting. We relate this gap to a missing cross-tier feedback abstraction, bridging the incommensurable per-tier signals and the LLM Orchestrator.
Antonino Vaccarella, Lan-Pei Li, Vincenzo Lomonaco et al.· 0 citations
This systematic review explores the intersection between Multi-Agent Systems and Digital Twins, with a particular focus on predictive maintenance applications in resource-constrained contexts and reveals that, despite significant progress, no existing system offers an integrated embedded-distributed hierarchical solution that simultaneously meets the requirements of Industry 5.0.
Korota Arsène Coulibaly, M. Hamlich· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
